Artificial intelligence and machine learning seminar

Due to the COVID-19 crisis, the information below is subject to change, in particular that concerning the teaching mode (presential, distance or in a comodal or hybrid format).

3 credits

30.0 h

Teacher(s)

Dupont Pierre; Nijssen Siegfried;

Language

English

Main themes

The topics covered in the seminar will address artificial intelligence and machine learning. In particular, scientific articles are selected in these fields.
On the one hand, students are confronted with problem of the quality of a scientific bibliography. Moreover, students read scientific literature (eg articles from international journals).

Aims

At the end of this learning unit, the student is able to :

Given the learning outcomes of the "Master in Computer Science and Engineering" program, this course contributes to the development, acquisition and evaluation of the following learning outcomes:

INFO1.1-3
INFO3.1, INFO3.2
INFO5.3-4, INFO5.6
INFO6.1, 6.4

Given the learning outcomes of the "Master [120] in Computer Science" program, this course contributes to the development, acquisition and evaluation of the following learning outcomes:

SINF1.M4
SINF3.1, SINF3.2
SINF5.3-4, SINF5.6
SINF6.1, SINF6.3, SINF6.4

Student completing successfully this course will be able to

establish the state of the art based on the scientific literature, when confronted with a research problem beyond his current knowledge,
prepare a comprehensive report including a scientific bibliography and explaining its relevance to a theme,
synthesize a scientific article by explaining the context, challenges, innovative results, potential applications as well as tracks for further work in the field,
communicate orally the results of a research to a public of computer scientists not experts in the field,
interact with a person who presents research results showing a critical and constructive look over the work presented.

Content

This seminar focuses on recent advances in artificial intelligence and machine learning.

Teaching methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

After a general introduction by the teacher, the seminar essentially consists of several talks given by the students.
Intermediary results are due before the final talks (by default, given by groups of several students), including intermediate report(s) and submission to the teacher of the talk that will be presented.
A feedback about these intermediary results is given to each group, either directly or through the Moodle site.
Given the sanitary situation, this seminar will be fully given online (distance learning) through Teams and the Moodle site.

Evaluation methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

The evaluation focuses on the quality of the presentations made by each student in front of the other participants to the seminar.
The overall grade consists of:

80% for the quality of the presentation (teaching quality, correctness of technical content, references, ...)
20% of the pro-activity of each student when attending other presentations (questions, additional comments, ...)

For the second session, the evaluation is based for 80% on a written report to the teacher the first day of the examination session + 20% for the participation grade during the year (grade fixed during the first session).

Other information

Online resources

https://moodleucl.uclouvain.be/course/view.php?id=4863

Bibliography

Des ouvrages ou articles recommandés sont mentionnés sur le site Moodle du cours.
Recommended textbooks or scientific papers are mentioned on the Moodle site for this course.

Faculty or entity

INFO

Programmes / formations proposant cette unité d'enseignement (UE)

Title of the programme

Sigle

Credits

Prerequisites

Aims

Master [120] in Computer Science and Engineering

INFO2M

Master [120] in Computer Science

SINF2M

Master [120] in Data Science Engineering

DATE2M

Master [120] in Data Science: Information Technology

DATI2M